path_proj = here::here()
path_source = file.path(path_proj, "source")
source(file.path(path_source, "simulation", "simulations_functions_final.R"))
##
## Attaching package: 'tidyr'
## The following object is masked from 'package:reshape2':
##
## smiths
source(file.path(path_source, "functions", "plot_function.R"))
##
## Attaching package: 'gridExtra'
## The following object is masked from 'package:dplyr':
##
## combine
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
source(file.path(path_source, "functions", "fit_function.R"))
source(file.path(path_source, "functions", "table_function.R"))
# place for draws
# mac
posterior_draws_path = file.path(Sys.getenv("HOME"), "Desktop", "draws", "testEach")
# windows
#posterior_draws_path = file.path(Sys.getenv("USERPROFILE"), "Desktop", "draws", "testEach")
#data path
data_save_path = file.path(path_proj, "data", "fitted_model", "simulation", "1. q_constant")
#models
q_constant <- file.path(path_proj, "source", "models",
"q-constant.stan")
b_constant <- file.path(path_proj, "source", "models",
"b-constant.stan")
b_rw <- file.path(path_proj, "source", "models",
"b-rw1.stan")
b_ou <- file.path(path_proj, "source", "models",
"b-ou.stan")
compiled_models <- list(
q_constant = cmdstan_model(q_constant),
b_constant = cmdstan_model(b_constant),
b_rw = cmdstan_model(b_rw),
b_ou = cmdstan_model(b_ou)
)
models_to_use <- c("q_constant", "b_constant", "b_rw", "b_ou")
simulate data - FR
setting
###### setting #####
seed <- 123
set.seed(seed)
# data
alpha_increase_seq_1 <- seq(10, 750, by = 30)
alpha_decrease_seq_1 <- seq(750, 10, by = -30)
alpha_lamb = c( rep(10,5), alpha_increase_seq_1 + rnorm(alpha_increase_seq_1,10,10),
alpha_decrease_seq_1 + rnorm(alpha_decrease_seq_1,10,10),
rep(10,5))
beta_lamb = 0.5
T = 60
# reprot delay
D <- 15;
# Time period for checking
D_check <- 5
first_date <- as.Date("2024-01-01")
scoreRange <- c(first_date+days(9), first_date+days(19), first_date+days(29),
first_date+days(39), first_date+days(49))
# q_constant_FR
params_q_constant_FR <- list(
data = list(
alpha_lamb = alpha_lamb,
beta_lamb = beta_lamb,
T = T,
date_start = first_date,
D = D
),
q_model = list(
method = "q_constant",
method_params = list(b = 0.7, phi = 0.9)
)
)
q_constant_FR <- simulateData(params_q_constant_FR)
# q_constant_NFR
params_q_constant_NFR <- list(
data = list(
alpha_lamb = alpha_lamb,
beta_lamb = beta_lamb,
T = T,
date_start = first_date,
D = D
),
q_model = list(
method = "q_constant",
method_params = list(b = 0.1, phi = 0.9)
)
)
q_constant_NFR <- simulateData(params_q_constant_NFR)
expplot
# exploritary analysis
page_num <- ceiling(nrow(q_constant_FR$case_reported_cumulated)/16)
exp_plot_q_constant <- fit_exp_plot(q_constant_FR$case_reported_cumulated,ncol = 4, nrow = 4, page = c(1:page_num), if_fit = T)
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
print(exp_plot_q_constant)
## $plots
## $plots[[1]]
##
## $plots[[2]]
##
## $plots[[3]]
##
## $plots[[4]]
##
##
## $coefficients
## b phi
## 1 0.5055333 0.068284699
## 2 0.5547189 0.061080516
## 3 0.7367248 0.068106350
## 4 1.0819349 0.002559996
## 5 0.8801655 0.052014065
## 6 0.7714955 0.073444643
## 7 0.6618841 0.082137331
## 8 0.7350497 0.101364168
## 9 0.6569562 0.067900661
## 10 0.7529487 0.119118549
## 11 0.6962667 0.100999200
## 12 0.6908501 0.087611444
## 13 0.7260712 0.105252887
## 14 0.7246881 0.069474558
## 15 0.7242846 0.102580180
## 16 0.6505762 0.113664245
## 17 0.6765901 0.084812645
## 18 0.7023962 0.076889900
## 19 0.6865660 0.108069599
## 20 0.7423705 0.095698268
## 21 0.7499525 0.096562958
## 22 0.7147604 0.105208998
## 23 0.7015282 0.089256697
## 24 0.7142811 0.096966733
## 25 0.7040346 0.084828227
## 26 0.6710329 0.085590224
## 27 0.7251725 0.094808391
## 28 0.6969755 0.094929707
## 29 0.6935165 0.101173557
## 30 0.7213171 0.108125228
## 31 0.7450026 0.094426217
## 32 0.6959939 0.105698896
## 33 0.6771576 0.099930732
## 34 0.7228220 0.110606835
## 35 0.7062824 0.095197996
## 36 0.7482875 0.081456830
## 37 0.7035790 0.116396157
## 38 0.6718279 0.130207795
## 39 0.7056283 0.092995274
## 40 0.7051379 0.100951520
## 41 0.6758787 0.100670058
## 42 0.7037410 0.088612736
## 43 0.7023240 0.072963928
## 44 0.6665807 0.081973264
## 45 0.6860273 0.100502178
## 46 0.7179368 0.088329028
## 47 0.7208294 0.103174027
## 48 0.6311429 0.101095981
## 49 0.7561507 0.113951339
## 50 0.6426656 0.092764470
## 51 0.6830333 0.101369111
## 52 0.6920994 0.079863195
## 53 0.6688082 0.081973827
## 54 0.6752151 0.117209703
## 55 0.7067910 0.063220636
## 56 0.8115918 0.221940971
## 57 0.7492494 0.134753278
## 58 0.6864893 0.041201336
## 59 0.6850925 0.061430331
## 60 0.5849492 0.038381252
exp_plot_q_constant$coefficients
## b phi
## 1 0.5055333 0.068284699
## 2 0.5547189 0.061080516
## 3 0.7367248 0.068106350
## 4 1.0819349 0.002559996
## 5 0.8801655 0.052014065
## 6 0.7714955 0.073444643
## 7 0.6618841 0.082137331
## 8 0.7350497 0.101364168
## 9 0.6569562 0.067900661
## 10 0.7529487 0.119118549
## 11 0.6962667 0.100999200
## 12 0.6908501 0.087611444
## 13 0.7260712 0.105252887
## 14 0.7246881 0.069474558
## 15 0.7242846 0.102580180
## 16 0.6505762 0.113664245
## 17 0.6765901 0.084812645
## 18 0.7023962 0.076889900
## 19 0.6865660 0.108069599
## 20 0.7423705 0.095698268
## 21 0.7499525 0.096562958
## 22 0.7147604 0.105208998
## 23 0.7015282 0.089256697
## 24 0.7142811 0.096966733
## 25 0.7040346 0.084828227
## 26 0.6710329 0.085590224
## 27 0.7251725 0.094808391
## 28 0.6969755 0.094929707
## 29 0.6935165 0.101173557
## 30 0.7213171 0.108125228
## 31 0.7450026 0.094426217
## 32 0.6959939 0.105698896
## 33 0.6771576 0.099930732
## 34 0.7228220 0.110606835
## 35 0.7062824 0.095197996
## 36 0.7482875 0.081456830
## 37 0.7035790 0.116396157
## 38 0.6718279 0.130207795
## 39 0.7056283 0.092995274
## 40 0.7051379 0.100951520
## 41 0.6758787 0.100670058
## 42 0.7037410 0.088612736
## 43 0.7023240 0.072963928
## 44 0.6665807 0.081973264
## 45 0.6860273 0.100502178
## 46 0.7179368 0.088329028
## 47 0.7208294 0.103174027
## 48 0.6311429 0.101095981
## 49 0.7561507 0.113951339
## 50 0.6426656 0.092764470
## 51 0.6830333 0.101369111
## 52 0.6920994 0.079863195
## 53 0.6688082 0.081973827
## 54 0.6752151 0.117209703
## 55 0.7067910 0.063220636
## 56 0.8115918 0.221940971
## 57 0.7492494 0.134753278
## 58 0.6864893 0.041201336
## 59 0.6850925 0.061430331
## 60 0.5849492 0.038381252
exp_b_data_q_constant<- data.frame( date = as.Date(rownames(q_constant_FR$case_reported_cumulated)),
b = exp_plot_q_constant$coefficients$b)
exp_b_plot_q_constant <- ggplot(exp_b_data_q_constant, aes(x = date, y = b)) +
geom_point(color = "black", size = 1.5) +
geom_smooth(method = "loess", se = TRUE,
color = "blue", fill = "grey", alpha = 0.5) +
theme_minimal() +
labs(x = NULL, y = "Y", title = "Smoothed Curve of parameter b")
print(exp_b_plot_q_constant)
## `geom_smooth()` using formula = 'y ~ x'
# exploritary analysis
page_num <- ceiling(nrow(q_constant_NFR$case_reported_cumulated)/16)
exp_plot_q_constant <- fit_exp_plot(q_constant_NFR$case_reported_cumulated,ncol = 4, nrow = 4, page = c(1:page_num), if_fit = T)
print(exp_plot_q_constant)
## $plots
## $plots[[1]]
##
## $plots[[2]]
##
## $plots[[3]]
##
## $plots[[4]]
##
##
## $coefficients
## b phi
## 1 0.1869946 -0.051001292
## 2 0.2164268 0.182978516
## 3 0.2322592 0.006665343
## 4 0.1226886 0.058841139
## 5 0.1339608 0.095413495
## 6 0.1448781 0.073409970
## 7 0.1869024 0.081341838
## 8 0.1740489 0.085342272
## 9 0.1679732 0.105031397
## 10 0.1562647 0.059657544
## 11 0.1602249 0.112346045
## 12 0.1594944 0.051112774
## 13 0.1604827 0.080301253
## 14 0.1750573 0.081823130
## 15 0.1659627 0.062328155
## 16 0.1561349 0.123258797
## 17 0.1615412 0.080535533
## 18 0.1586075 0.094762094
## 19 0.1665503 0.091766855
## 20 0.1668306 0.079700003
## 21 0.1640436 0.060326591
## 22 0.1681521 0.070888959
## 23 0.1688694 0.070063237
## 24 0.1590684 0.076071431
## 25 0.1707159 0.066487319
## 26 0.1677933 0.078593650
## 27 0.1662205 0.097874077
## 28 0.1710149 0.070876171
## 29 0.1607356 0.082807334
## 30 0.1708570 0.094916517
## 31 0.1688358 0.083794619
## 32 0.1724922 0.084044119
## 33 0.1592873 0.064842692
## 34 0.1706777 0.076979756
## 35 0.1632874 0.087194990
## 36 0.1689219 0.071887629
## 37 0.1751177 0.084623374
## 38 0.1683295 0.079353454
## 39 0.1571803 0.084286223
## 40 0.1665454 0.061380520
## 41 0.1638938 0.084909013
## 42 0.1731742 0.078762578
## 43 0.1738430 0.062129233
## 44 0.1619723 0.090494047
## 45 0.1637851 0.093924222
## 46 0.1624054 0.077472768
## 47 0.1628068 0.064622423
## 48 0.1778563 0.125616206
## 49 0.1771074 0.064658509
## 50 0.1558917 0.067076838
## 51 0.1705677 0.077697590
## 52 0.1950076 0.057534643
## 53 0.1581472 0.044804716
## 54 0.2011045 0.019402256
## 55 0.1778789 0.066105321
## 56 0.1722104 0.004072393
## 57 0.1856203 0.017189050
## 58 0.1653274 0.127217678
## 59 0.1801947 -0.074344767
## 60 0.1878984 0.298906638
exp_plot_q_constant$coefficients
## b phi
## 1 0.1869946 -0.051001292
## 2 0.2164268 0.182978516
## 3 0.2322592 0.006665343
## 4 0.1226886 0.058841139
## 5 0.1339608 0.095413495
## 6 0.1448781 0.073409970
## 7 0.1869024 0.081341838
## 8 0.1740489 0.085342272
## 9 0.1679732 0.105031397
## 10 0.1562647 0.059657544
## 11 0.1602249 0.112346045
## 12 0.1594944 0.051112774
## 13 0.1604827 0.080301253
## 14 0.1750573 0.081823130
## 15 0.1659627 0.062328155
## 16 0.1561349 0.123258797
## 17 0.1615412 0.080535533
## 18 0.1586075 0.094762094
## 19 0.1665503 0.091766855
## 20 0.1668306 0.079700003
## 21 0.1640436 0.060326591
## 22 0.1681521 0.070888959
## 23 0.1688694 0.070063237
## 24 0.1590684 0.076071431
## 25 0.1707159 0.066487319
## 26 0.1677933 0.078593650
## 27 0.1662205 0.097874077
## 28 0.1710149 0.070876171
## 29 0.1607356 0.082807334
## 30 0.1708570 0.094916517
## 31 0.1688358 0.083794619
## 32 0.1724922 0.084044119
## 33 0.1592873 0.064842692
## 34 0.1706777 0.076979756
## 35 0.1632874 0.087194990
## 36 0.1689219 0.071887629
## 37 0.1751177 0.084623374
## 38 0.1683295 0.079353454
## 39 0.1571803 0.084286223
## 40 0.1665454 0.061380520
## 41 0.1638938 0.084909013
## 42 0.1731742 0.078762578
## 43 0.1738430 0.062129233
## 44 0.1619723 0.090494047
## 45 0.1637851 0.093924222
## 46 0.1624054 0.077472768
## 47 0.1628068 0.064622423
## 48 0.1778563 0.125616206
## 49 0.1771074 0.064658509
## 50 0.1558917 0.067076838
## 51 0.1705677 0.077697590
## 52 0.1950076 0.057534643
## 53 0.1581472 0.044804716
## 54 0.2011045 0.019402256
## 55 0.1778789 0.066105321
## 56 0.1722104 0.004072393
## 57 0.1856203 0.017189050
## 58 0.1653274 0.127217678
## 59 0.1801947 -0.074344767
## 60 0.1878984 0.298906638
exp_b_data_q_constant<- data.frame( date = as.Date(rownames(q_constant_NFR$case_reported_cumulated)),
b = exp_plot_q_constant$coefficients$b)
exp_b_plot_q_constant <- ggplot(exp_b_data_q_constant, aes(x = date, y = b)) +
geom_point(color = "black", size = 1.5) +
geom_smooth(method = "loess", se = TRUE,
color = "blue", fill = "grey", alpha = 0.5) +
theme_minimal() +
labs(x = NULL, y = "Y", title = "Smoothed Curve of parameter b")
print(exp_b_plot_q_constant)
## `geom_smooth()` using formula = 'y ~ x'
fit model
out_q_constant_FR <- nowcasting_moving_window(q_constant_FR$case_reported_cumulated, scoreRange = scoreRange,
case_true = q_constant_FR$case_true,
start_date = first_date,
D = D, seeds = seed,
methods =models_to_use,
compiled_models = compiled_models,
iter_sampling = 2000, iter_warmup = 1000, refresh = 0,
num_chains = 3, suppress_output = T,
posterior_draws_path = file.path(posterior_draws_path, "q_constant")
)
## ====================
## now=2024-01-10 (1/5)
## ====================
## Warning in nowcasting_moving_window(q_constant_FR$case_reported_cumulated, :
## The number of rows of the input data is smaller than number of max delay D,
## which might cause inaccuracy.
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 0.8 seconds.
## Chain 2 finished in 0.6 seconds.
## Chain 3 finished in 0.7 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 0.7 seconds.
## Total execution time: 2.4 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 0.3 seconds.
## Chain 2 finished in 0.2 seconds.
## Chain 3 finished in 0.2 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 0.3 seconds.
## Total execution time: 1.1 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.9 seconds.
## Chain 2 finished in 3.0 seconds.
## Chain 3 finished in 1.7 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 2.2 seconds.
## Total execution time: 6.9 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.7 seconds.
## Chain 2 finished in 3.6 seconds.
## Chain 3 finished in 3.3 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 2.8 seconds.
## Total execution time: 8.8 seconds.
##
## ====================
## now=2024-01-20 (2/5)
## ====================
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.2 seconds.
## Chain 2 finished in 1.3 seconds.
## Chain 3 finished in 1.2 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 1.2 seconds.
## Total execution time: 4.0 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 0.4 seconds.
## Chain 2 finished in 0.3 seconds.
## Chain 3 finished in 0.3 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 0.3 seconds.
## Total execution time: 1.4 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 3.8 seconds.
## Chain 2 finished in 5.5 seconds.
## Chain 3 finished in 6.2 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 5.2 seconds.
## Total execution time: 15.8 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 6.3 seconds.
## Chain 2 finished in 4.0 seconds.
## Chain 3 finished in 4.0 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 4.8 seconds.
## Total execution time: 14.6 seconds.
##
## ====================
## now=2024-01-30 (3/5)
## ====================
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.9 seconds.
## Chain 2 finished in 1.9 seconds.
## Chain 3 finished in 1.7 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 1.9 seconds.
## Total execution time: 5.9 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 0.6 seconds.
## Chain 2 finished in 0.6 seconds.
## Chain 3 finished in 0.5 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 0.6 seconds.
## Total execution time: 2.0 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 8.6 seconds.
## Chain 2 finished in 8.9 seconds.
## Chain 3 finished in 8.6 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 8.7 seconds.
## Total execution time: 26.6 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 7.8 seconds.
## Chain 2 finished in 5.6 seconds.
## Chain 3 finished in 7.3 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 6.9 seconds.
## Total execution time: 20.9 seconds.
##
## ====================
## now=2024-02-09 (4/5)
## ====================
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 3.0 seconds.
## Chain 2 finished in 3.0 seconds.
## Chain 3 finished in 2.9 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 3.0 seconds.
## Total execution time: 9.3 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 0.8 seconds.
## Chain 2 finished in 0.8 seconds.
## Chain 3 finished in 1.1 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 0.9 seconds.
## Total execution time: 3.0 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 10.7 seconds.
## Chain 2 finished in 10.0 seconds.
## Chain 3 finished in 12.9 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 11.2 seconds.
## Total execution time: 34.0 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 5.6 seconds.
## Chain 2 finished in 7.2 seconds.
## Chain 3 finished in 10.5 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 7.8 seconds.
## Total execution time: 23.7 seconds.
##
## ====================
## now=2024-02-19 (5/5)
## ====================
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 3.4 seconds.
## Chain 2 finished in 3.7 seconds.
## Chain 3 finished in 3.4 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 3.5 seconds.
## Total execution time: 10.7 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.2 seconds.
## Chain 2 finished in 1.0 seconds.
## Chain 3 finished in 1.1 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 1.1 seconds.
## Total execution time: 3.5 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 20.3 seconds.
## Chain 2 finished in 18.1 seconds.
## Chain 3 finished in 15.7 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 18.1 seconds.
## Total execution time: 54.4 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 24.1 seconds.
## Chain 2 finished in 9.9 seconds.
## Chain 3 finished in 11.5 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 15.2 seconds.
## Total execution time: 45.9 seconds.
save(out_q_constant_FR, file = file.path(data_save_path, "FR_q_constant.RData"))
#load( file.path(data_save_path, "FR_q_constant.RData"))
#
results_q_constant_FR <- nowcasts_table(out_q_constant_FR, D = D, report_unit = "day",
methods = models_to_use
)
plots_q_constant_FR <- nowcasts_plot(results_q_constant_FR, D = D, report_unit = "day",
methods = models_to_use
)
## Warning: The `size` argument of `element_rect()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
for (i in 1:length(results_q_constant_FR)) {
print(calculate_metrics(results_q_constant_FR[[i]],
methods = models_to_use))
}
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 157.46 85.67 92.62 81.61 181.01 0.5 q_constant
## 2 35.79 13.62 14.30 7.79 78.01 1.0 b_constant
## 3 30.38 11.78 12.66 6.89 94.11 1.0 b_rw
## 4 28.22 11.12 12.06 7.03 90.00 1.0 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 54.72 11.32 41.10 11.05 114.11 0.9 q_constant
## 2 7.38 1.65 4.43 1.35 88.31 1.0 b_constant
## 3 7.70 1.50 4.66 1.29 101.36 1.0 b_rw
## 4 6.68 1.57 3.96 1.25 98.91 1.0 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 57.22 4.74 24.59 2.93 115.21 0.97 q_constant
## 2 44.77 3.59 11.45 1.46 109.64 1.00 b_constant
## 3 37.72 3.05 10.15 1.31 117.88 1.00 b_rw
## 4 43.37 3.46 10.83 1.35 116.24 1.00 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 18.10 1.85 13.03 1.56 116.76 1 q_constant
## 2 8.50 1.18 4.79 0.81 114.83 1 b_constant
## 3 9.83 1.24 4.58 0.76 117.83 1 b_rw
## 4 5.92 1.09 3.54 0.72 117.93 1 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 11.44 2.12 8.25 1.35 110.09 1 q_constant
## 2 9.32 2.15 4.43 0.98 109.27 1 b_constant
## 3 10.40 2.42 4.34 1.02 109.53 1 b_rw
## 4 9.32 2.21 4.12 0.98 109.91 1 b_ou
for (i in 1:length(results_q_constant_FR)) {
print(calculate_metrics(data.table::last(results_q_constant_FR[[i]], D_check),
methods = models_to_use))
}
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 222.30 97.55 172.41 92.30 329.42 0 q_constant
## 2 50.61 18.74 27.80 11.30 138.21 1 b_constant
## 3 42.96 16.30 24.69 10.46 169.80 1 b_rw
## 4 39.89 15.07 23.27 9.77 161.40 1 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 90.24 12.04 86.58 11.88 255.24 1 q_constant
## 2 14.42 2.11 13.79 2.00 196.63 1 b_constant
## 3 15.13 2.12 14.99 2.11 247.00 1 b_rw
## 4 13.10 1.94 12.54 1.83 237.21 1 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 134.31 10.18 82.13 6.17 274.62 0.8 q_constant
## 2 109.45 8.33 58.00 4.46 261.01 1.0 b_constant
## 3 92.16 7.02 50.37 3.88 303.04 1.0 b_rw
## 4 106.06 8.07 55.43 4.26 296.02 1.0 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 36.08 3.45 32.58 3.01 227.22 1 q_constant
## 2 21.74 2.10 20.14 1.88 223.43 1 b_constant
## 3 25.75 2.46 18.77 1.79 240.81 1 b_rw
## 4 13.58 1.19 11.76 1.03 244.41 1 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 26.07 5.81 22.57 4.85 146.62 1 q_constant
## 2 27.15 6.25 21.37 4.80 145.60 1 b_constant
## 3 31.71 7.24 25.72 5.63 153.22 1 b_rw
## 4 27.81 6.42 22.11 4.95 151.00 1 b_ou
plots_q_constant_FR
## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
out_q_constant_NFR <- nowcasting_moving_window(q_constant_NFR$case_reported_cumulated, scoreRange = scoreRange,
case_true = q_constant_NFR$case_true,
start_date = first_date,
D = D, seeds = seed,
methods =models_to_use,
compiled_models = compiled_models,
iter_sampling = 2000, iter_warmup = 1000, refresh = 0,
num_chains = 3, suppress_output = T,
posterior_draws_path = file.path(posterior_draws_path, "q_constant")
)
## ====================
## now=2024-01-10 (1/5)
## ====================
## Warning in nowcasting_moving_window(q_constant_NFR$case_reported_cumulated, :
## The number of rows of the input data is smaller than number of max delay D,
## which might cause inaccuracy.
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 0.6 seconds.
## Chain 2 finished in 0.6 seconds.
## Chain 3 finished in 0.6 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 0.6 seconds.
## Total execution time: 2.0 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 0.3 seconds.
## Chain 2 finished in 0.3 seconds.
## Chain 3 finished in 0.2 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 0.3 seconds.
## Total execution time: 1.2 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.9 seconds.
## Chain 2 finished in 2.2 seconds.
## Chain 3 finished in 1.7 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 1.9 seconds.
## Total execution time: 6.2 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 2.1 seconds.
## Chain 2 finished in 4.4 seconds.
## Chain 3 finished in 3.8 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 3.4 seconds.
## Total execution time: 10.6 seconds.
##
## ====================
## now=2024-01-20 (2/5)
## ====================
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.3 seconds.
## Chain 2 finished in 1.4 seconds.
## Chain 3 finished in 1.3 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 1.4 seconds.
## Total execution time: 4.3 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 0.9 seconds.
## Chain 2 finished in 0.9 seconds.
## Chain 3 finished in 1.0 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 0.9 seconds.
## Total execution time: 3.1 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 9.1 seconds.
## Chain 2 finished in 7.7 seconds.
## Chain 3 finished in 7.0 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 7.9 seconds.
## Total execution time: 24.2 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 5.7 seconds.
## Chain 2 finished in 5.8 seconds.
## Chain 3 finished in 5.4 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 5.6 seconds.
## Total execution time: 17.1 seconds.
##
## ====================
## now=2024-01-30 (3/5)
## ====================
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.7 seconds.
## Chain 2 finished in 1.6 seconds.
## Chain 3 finished in 1.5 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 1.6 seconds.
## Total execution time: 5.1 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.5 seconds.
## Chain 2 finished in 1.2 seconds.
## Chain 3 finished in 1.3 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 1.3 seconds.
## Total execution time: 4.3 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 14.4 seconds.
## Chain 2 finished in 11.7 seconds.
## Chain 3 finished in 5.3 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 10.5 seconds.
## Total execution time: 31.7 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 6.7 seconds.
## Chain 2 finished in 9.8 seconds.
## Chain 3 finished in 7.2 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 7.9 seconds.
## Total execution time: 24.0 seconds.
##
## ====================
## now=2024-02-09 (4/5)
## ====================
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 1.9 seconds.
## Chain 2 finished in 1.8 seconds.
## Chain 3 finished in 2.0 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 1.9 seconds.
## Total execution time: 6.0 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 2.2 seconds.
## Chain 2 finished in 2.2 seconds.
## Chain 3 finished in 1.8 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 2.1 seconds.
## Total execution time: 6.5 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 17.7 seconds.
## Chain 2 finished in 19.1 seconds.
## Chain 3 finished in 16.1 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 17.6 seconds.
## Total execution time: 53.1 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 9.9 seconds.
## Chain 2 finished in 12.2 seconds.
## Chain 3 finished in 11.7 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 11.3 seconds.
## Total execution time: 34.1 seconds.
##
## ====================
## now=2024-02-19 (5/5)
## ====================
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 2.5 seconds.
## Chain 2 finished in 3.6 seconds.
## Chain 3 finished in 3.0 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 3.0 seconds.
## Total execution time: 9.4 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 2.2 seconds.
## Chain 2 finished in 2.4 seconds.
## Chain 3 finished in 2.5 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 2.4 seconds.
## Total execution time: 7.5 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 36.2 seconds.
## Chain 2 finished in 35.9 seconds.
## Chain 3 finished in 37.0 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 36.4 seconds.
## Total execution time: 109.4 seconds.
##
## Running MCMC with 3 sequential chains...
##
## Chain 1 finished in 17.0 seconds.
## Chain 2 finished in 14.3 seconds.
## Chain 3 finished in 15.7 seconds.
##
## All 3 chains finished successfully.
## Mean chain execution time: 15.7 seconds.
## Total execution time: 47.5 seconds.
save(out_q_constant_NFR, file = file.path(data_save_path, "NFR_q_constant.RData"))
#load( file.path(data_save_path, "NFR_q_constant.RData"))
results_q_constant_NFR <- nowcasts_table(out_q_constant_NFR, D = D, report_unit = "day",
methods = models_to_use
)
plots_q_constant_NFR <- nowcasts_plot(results_q_constant_NFR, D = D, report_unit = "day",
methods = models_to_use
)
for (i in 1:length(results_q_constant_NFR)) {
print(calculate_metrics(results_q_constant_NFR[[i]],
methods = models_to_use))
}
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 36.58 20.70 17.67 16.52 89.91 1.0 q_constant
## 2 67.76 43.80 43.25 41.74 55.80 0.6 b_constant
## 3 75.73 47.06 48.13 44.76 58.31 0.6 b_rw
## 4 71.18 45.87 45.85 43.88 57.91 0.5 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 100.98 19.92 73.16 18.61 106.26 0.45 q_constant
## 2 60.76 11.51 38.69 9.97 126.71 0.95 b_constant
## 3 89.34 14.66 57.89 12.64 168.31 0.90 b_rw
## 4 68.05 12.32 43.71 10.66 151.31 0.95 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 165.92 20.03 131.74 19.36 109.51 0.2 q_constant
## 2 23.80 6.37 16.55 4.51 133.41 1.0 b_constant
## 3 53.24 6.60 34.33 5.45 196.38 1.0 b_rw
## 4 26.79 6.24 17.40 4.45 176.92 1.0 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 190.31 19.85 160.10 19.32 110.26 0.15 q_constant
## 2 23.59 5.70 16.21 3.62 134.86 1.00 b_constant
## 3 33.38 5.87 21.24 4.06 176.19 1.00 b_rw
## 4 22.18 5.69 15.33 3.56 159.94 1.00 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 182.01 19.98 154.70 19.42 102.63 0.16 q_constant
## 2 23.60 6.06 16.44 3.77 122.15 0.98 b_constant
## 3 23.01 5.88 16.13 3.78 139.49 1.00 b_rw
## 4 23.23 6.05 15.50 3.69 135.75 0.98 b_ou
for (i in 1:length(results_q_constant_NFR)) {
print(calculate_metrics(data.table::last(results_q_constant_NFR[[i]],D_check),
methods = models_to_use))
}
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 51.63 20.08 32.43 14.85 155.61 1.0 q_constant
## 2 95.51 48.46 79.38 47.49 94.61 0.4 b_constant
## 3 106.81 53.61 88.98 52.67 100.21 0.4 b_rw
## 4 100.34 51.22 84.35 50.50 99.62 0.2 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 168.69 21.23 157.22 20.19 232.81 0.4 q_constant
## 2 103.96 12.75 82.61 10.41 281.03 1.0 b_constant
## 3 160.54 20.00 143.88 18.36 414.44 0.8 b_rw
## 4 117.53 14.47 96.57 12.23 349.63 1.0 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 275.74 19.99 273.53 19.88 259.43 0 q_constant
## 2 33.46 2.39 25.57 1.83 320.03 1 b_constant
## 3 91.33 6.57 81.51 5.89 543.24 1 b_rw
## 4 35.47 2.54 26.69 1.92 445.67 1 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 229.46 20.47 226.20 20.29 216.22 0 q_constant
## 2 40.44 3.53 31.29 2.77 266.42 1 b_constant
## 3 67.89 6.14 62.03 5.62 388.63 1 b_rw
## 4 39.48 3.46 32.36 2.89 323.02 1 b_ou
## RMSE RMSPE MAE MAPE Interval_Width Coverage_Rate Method
## 1 108.14 21.27 98.97 19.84 139.02 0.4 q_constant
## 2 45.03 9.85 35.58 7.52 171.81 0.8 b_constant
## 3 45.66 9.89 40.13 8.48 197.00 1.0 b_rw
## 4 44.95 9.85 34.97 7.40 177.41 0.8 b_ou
plots_q_constant_NFR
## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
